Last verified
PRIOR GENERATIONNO DISCOUNT ATTACHEDOPENAI-COMPATIBLECACHED INPUT -90%KOREA - UPSTAGE

Solar Pro 2 API Pricing

Solar Pro 2 is the prior Upstage enterprise tier — high-performance enterprise llm for complex reasoning and generation. Upstage lists it at $0.15/M input, $0.015/M cached input and $0.60/M output, which is half the list rate of Solar Pro 4 on every dimension. Note the timing trap: while Solar Pro 4's launch discount runs, the flagship is the cheaper of the two — that reverses on September 11, 2026.

Input - per 1M tokens
$0.15/M
Half of Solar Pro 4 list
Output - per 1M tokens
$0.60/M
Half of Solar Pro 4 list
Cached input
$0.015/M
Prompt cache Upstage row -90%
Effective - agentic blend
$0.0842/M
92/8 split - 82% cache
§ 01 / TERMINAL

Run the numbers.

Calculator pre-loaded with Solar Pro 2's rates. No discount applies to this model, so these are the figures you are billed today and after September 11.

$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
Words equivalent (English)
Effective rate
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Real-world presets.

§ 03 / TOKENIZER

Paste text. See tokens. See cost.

Estimate · solar-tokenizer-estimate · ≈3.8 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 351
Words 57
Tokens (estimated) 92 tokens
Cost as input · uncached $0.00001 USD
Cost as output · uncached $0.00006 USD
Cost as cached input $0.000001 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Solar Pro 4 $0.30 cache $0.06 $1.20 $0.191 agentic flagship Not published Tool calling and terminal work
Solar Pro 3 $0.15 cache $0.015 $0.60 $0.0842 half the flagship rate Not published Reasoning and instruction following
Solar Pro 2 Current $0.15 cache $0.015 $0.60 $0.0842 same card as Pro 3 Not published Enterprise reasoning, prior gen
GLM-4.7 $0.60 cache $0.11 $2.20 $0.358 Zhipu coding tier 200K Comparable Chinese coding model

Frequently asked.

Solar Pro 2 pricing questions, and how it sits against the rest of the Solar line.

Q · 01 How much does Solar Pro 2 cost? +
$0.15/M input, $0.015/M cached input and $0.60/M output, from Upstage's own rate card. No discount is attached to this model.
Q · 02 Is Solar Pro 2 cheaper than Solar Pro 4? +
On list price, yes — exactly half on every dimension. Today, no. Solar Pro 4's launch discount of 90% runs until September 10, 2026, which puts the flagship at $0.03 / $0.12 against this model's $0.15 / $0.60. The ordering flips back on September 11.
Q · 03 How does it differ from the other Solar tier at this price? +
Solar Pro 2 and Solar Pro 3 carry an identical rate card. Upstage positions Pro 3 as the newer build with stronger reasoning and instruction following, and Pro 2 as the enterprise generation before it. Since the price is the same, there is no cost reason to stay on the older one.
Q · 04 What context window does it have? +
Upstage publishes no context window for the Solar models on any first-party page we could find on August 16, 2026. We show nothing rather than copy a figure from an aggregator.
Q · 05 How do I call it? +
The API is OpenAI-compatible: point the OpenAI SDK at https://api.upstage.ai/v1 and pass solar-pro2. Rate limits are 100 requests/min and 50,000 tokens/min.